Churn Prevention Using Deep Convolutional Neural Networks and Autoencoders
Understanding and preventing churn is important for both small and large businesses to maintain and grow revenue. We will describe both unsupervised and supervised machine learning methods for smarter targeted marketing. We discuss how deep convolutional neural networks can predict churn, and how autoencoders can uncover patterns of customers that churn. By combining these two methods, marketing efforts can be more targeted and effective.
Art Wangperawong is an American-born Chinese with roots from Thailand. He built AI systems for some of the largest conglomerates in Asia and has experience in energy, medicine, telecommunications, finance, semiconductors, IT and education. He has given lectures in the US and Asia and enjoys studying languages such as Thai, Korean, Mandarin, Cantonese and Teochew. Art studied at Stanford University, where he obtained a B.S. in Mechanical Engineering as well as an M.S. and a Ph.D. in Electrical Engineering.